Morsali, Mahdi (Linköping University), Aaslund, Jan (Linköping Univ), Frisk, Erik (Linköping University)

Trajectory Planning in Traffic Scenarios Using Support Vector Machines

Scheduled for presentation during the Regular Session "Motion and Path Planning for Autonomous Vehicle" (MoBT1), Monday, June 24, 2019, 16:10−16:30, Chambord

9th IFAC International Symposium on Advances in Automotive Control, June 23-27, 2019, Orléans, France

This information is tentative and subject to change. Compiled on April 23, 2024

Abstract

Finding safe and collision free trajectories in an environment with moving obstacles is central for autonomous vehicles but at the same time a complex task. A reason is that the search space in space-time domain is very complex. This paper proposes a two-step approach where in first step, the search space for trajectory planning is simplified by solving a convex optimization problem formulated as a Support Vector Machine resulting in an obstacle free corridor that is suitable for a trajectory planner. Then, in a second step, a basic A* search strategy is used in the obstacle free search space. Due to the physical model used, the comfort and safety criteria are applied while searching the trajectory. The vehicle rollover prevention is used as a safety criterion and the acceleration, jerk and steering angle limits are used as comfort criteria. For simulations, urban environments with intersections and vehicles as moving obstacles are constructed. The properties of the approach are examined by the simulation results.